Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 67655
    Prev
    Next
    INDEX
    Explanations

    Syracuse and news references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inde
    -0.30
    .utility
    -0.27
    essian
    -0.25
    çļĦçĪ¶äº²
    -0.25
     increments
    -0.25
     Rou
    -0.25
    飲ãģ¿
    -0.25
     Incre
    -0.25
    æ¿ĢåĬ¨
    -0.25
    credible
    -0.24
    POSITIVE LOGITS
     ster
    0.27
     />\
    0.26
    BILL
    0.25
    çĽħ
    0.25
    /dom
    0.25
    <tbody
    0.25
     "</
    0.24
    åħ»
    0.24
    Bill
    0.24
    西çͲ
    0.24
    Activations Density 0.033%

    No Known Activations